Yuanqiu Mo
Papers
1
Total Citations
5
H-Index
1
About
Yuanqiu Mo is a rising researcher in the field of multi-agent reinforcement learning (MARL), with a focus on developing theoretically grounded algorithms for networked systems. His key research areas include distributed optimization, neural policy gradient methods, and the convergence analysis of reinforcement learning in multi-agent environments. Mo’s most notable contribution is the introduction of a distributed neural policy gradient algorithm that achieves global convergence for networked multi-agent reinforcement learning, addressing a critical limitation of prior approaches that relied on linear function approximation and thus suffered from poor expressivity. This work, published in 2025 and already garnering 5 citations, demonstrates his ability to tackle complex, real-world coordination problems where agents must collaboratively maximize discounted cumulative rewards. By bridging the gap between neural network-based policy learning and rigorous convergence guarantees, Mo’s research has significant implications for applications such as autonomous vehicle coordination, robotic swarms, and smart grid management. His work stands out for its theoretical depth and practical relevance, marking him as a promising contributor to the advancement of scalable, intelligent multi-agent systems.
Research Focus
Key Achievements
Top Papers
- 1